linux-kernel - Re: [GIT PULL 0/5] perf/urgent fixes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:	Sun, 29 May 2011 16:30:05 +0200
From:	Ingo Molnar <mingo@...e.hu>
To:	Arnaldo Carvalho de Melo <acme@...radead.org>
Cc:	linux-kernel@...r.kernel.org, David Ahern <dsahern@...il.com>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Mike Galbraith <efault@....de>,
	Paul Mackerras <paulus@...ba.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Stephane Eranian <eranian@...gle.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	Tom Zanussi <tzanussi@...il.com>
Subject: Re: [GIT PULL 0/5] perf/urgent fixes


* Arnaldo Carvalho de Melo <acme@...radead.org> wrote:

> Em Sat, May 28, 2011 at 11:41:50AM +0200, Ingo Molnar escreveu:
> > The various variations of kptr_restrict now work fine AFAICS - will 
> > send the fixes to Linus today.
> > 
> > One (very) small issue i noticed, if the user only samples user-space 
> > events then i still get the warning:
> > 
> >  aldebaran:~> perf record -e cycles:upp sleep 1
> >  WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,
> > 
> > although perf does not record any kernel samples so kptr_restrict is 
> > irrelevant in this case.
> 
> I'll have that fixed too, oversight. We really should avoid 
> confusing messages, and this one, as you mention, seems just noise 
> as I still have to look again how vsyscall symbols get resolved, 
> IIRC they need a kernel symtab, but then, if that is the case, the 
> message should be changed accordingly.

Btw., if you touch that code, would you be interested in adding a 
--user-events kind of option which would have the implicit effect of 
adding :u to every event that is listed (or implied)? (and a 
--kernel-events counterpart, for :k)

The reason is that right now there's no easy way to run say 'perf 
stat -ddd' but measure userspace events only.

[ perf record --repeat would be nice as well :-) And a pony! ]

Thanks,

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/